Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:280f24b69ed2f388e06fe78ab19f755b372c01f593abbb544fff93efa4098e07
+oid sha256:6ae05965162aa06eb88bf36cda7caef25229591c906e5d97e19d64b11ccaaba5
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67b6a63014dfc8220d6c4ebd78976e4d61bf5ca40b12c9d8617dfaedb7bf006c
+oid sha256:e1de161225d142d6a89e02265ba2f3f35155c52ceb5f2308b745a95d2890ece9
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:926d0f02ed35ff822c8351520aea564c896c73584b204d9f89321ceacb12846d
+oid sha256:354336e3d2096475e2dbe89576e77c5e214cdcb69bb19ba1dc01b08c50a83b5a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
+oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2894083261489868,
-  "best_model_checkpoint": "./outputs/checkpoint-500",
-  "epoch": 0.6666666666666666,
+  "best_metric": 1.2811017036437988,
+  "best_model_checkpoint": "./outputs/checkpoint-600",
+  "epoch": 0.8,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,20 @@
       "eval_samples_per_second": 15.261,
       "eval_steps_per_second": 1.914,
       "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002,
+      "loss": 1.1142,
+      "step": 600
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.2811017036437988,
+      "eval_runtime": 126.9356,
+      "eval_samples_per_second": 15.205,
+      "eval_steps_per_second": 1.906,
+      "step": 600
     }
   ],
   "logging_steps": 100,
@@ -84,7 +98,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.7727133699817472e+16,
+  "total_flos": 2.126816116772045e+16,
   "trial_name": null,
   "trial_params": null
 }